44 lines
1018 B
TOML
44 lines
1018 B
TOML
[project]
|
|
name = "codebert-training"
|
|
version = "1.0.0"
|
|
description = "This code is used to train CodeBERT"
|
|
authors = [
|
|
{name = "Patryk Bartkowiak", email = "patbar15@st.amu.edu.pl"},
|
|
]
|
|
dependencies = [
|
|
"wandb==0.18.5",
|
|
"torch==2.5.1",
|
|
"tqdm==4.66.5",
|
|
"tree-sitter==0.23.1",
|
|
"transformers[torch]==4.46.3",
|
|
"datasets==3.0.1",
|
|
"huggingface-hub==0.26.0",
|
|
"matplotlib==3.9.2",
|
|
"scikit-learn==1.5.2",
|
|
"seaborn==0.13.2",
|
|
"tree-sitter-python==0.23.4",
|
|
"ipykernel==6.29.5",
|
|
"ipywidgets==8.1.5",
|
|
]
|
|
requires-python = "==3.11.*"
|
|
readme = "README.md"
|
|
license = {text = "MIT"}
|
|
|
|
[[tool.pdm.source]]
|
|
url = "https://download.pytorch.org/whl/cu124"
|
|
verify_ssl = true
|
|
include_packages = ["torch", "torchvision", "torchaudio"]
|
|
name = "cuda"
|
|
|
|
[build-system]
|
|
requires = ["pdm-backend"]
|
|
build-backend = "pdm.backend"
|
|
|
|
[tool.pdm]
|
|
distribution = true
|
|
|
|
[tool.pdm.scripts]
|
|
parse_dataset = {cmd = "src/parse_dataset.py"}
|
|
train = {cmd = "src/training.py"}
|
|
eval = {cmd = "src/eval_model.py"}
|